CN111931586A - Face age identification method and device and storage medium - Google Patents
Face age identification method and device and storage medium Download PDFInfo
- Publication number
- CN111931586A CN111931586A CN202010676911.1A CN202010676911A CN111931586A CN 111931586 A CN111931586 A CN 111931586A CN 202010676911 A CN202010676911 A CN 202010676911A CN 111931586 A CN111931586 A CN 111931586A
- Authority
- CN
- China
- Prior art keywords
- age
- face
- identification
- acquiring
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a face age identification method, a device and a storage medium, comprising the following steps: a face feature acquisition step, namely acquiring face feature vectors with fixed channel numbers according to a backbone network of a face depth recognition model based on a face age data set; an age model training step, namely training and generating a plurality of age-classified age recognition models through two layers of neural networks according to the face feature vector; and an age identification step, namely acquiring a face picture to be identified, acquiring a face feature vector to be identified according to the backbone network of the face depth identification model, and acquiring an identification age according to the age identification model. According to the invention, the existing face deep recognition model is reused to obtain the face characteristic vector processed in face recognition, and the shallow age model is trained and recognized, so that the recognition precision is improved, the deep age recognition learning model does not need to be repeatedly constructed, and manpower and material resources are saved.
Description
Technical Field
The present invention relates to the field of face recognition technologies, and in particular, to a face age recognition method, a face age recognition device, and a storage medium.
Background
Face recognition is a biometric technology for identity recognition based on facial feature information of a person. With the maturity of the technology and the improvement of social acceptance, face recognition is widely applied in various fields.
There are two types of methods for predicting age attributes based on human faces, one is to extract features of several key points by a traditional image processing mode, and then calculate and predict the extracted features by a shallow method, so as to predict a specific age result, and the method has the advantages of high speed and low precision; the other type is to use a deep learning mode to learn and train a deep neural network model for age identification, and although the accuracy is higher, the calculation speed is slow.
Disclosure of Invention
The present invention is directed to solving at least one of the problems of the prior art. Therefore, the invention provides a face age identification method which can improve the identification precision.
The invention also provides a face age identification device with the face age identification method.
The invention also provides a storage medium with the face age identification method.
According to the embodiment of the first aspect of the invention, the face age identification method comprises the following steps: a face feature acquisition step, namely acquiring face feature vectors with fixed channel numbers according to a backbone network of a face depth recognition model based on a face age data set; an age model training step, namely learning and training to generate a plurality of age-classified age identification models through two layers of neural networks according to the face feature vector; and an age identification step, namely acquiring a face picture to be identified, acquiring a face feature vector to be identified according to the backbone network of the face depth identification model, and acquiring an identification age according to the age identification model.
The face age identification method provided by the embodiment of the invention at least has the following beneficial effects: the existing face deep recognition model is reused, the face characteristic vector processed in face recognition is obtained, the shallow age model is trained and recognized, recognition accuracy is improved, the deep age recognition learning model does not need to be repeatedly constructed, and manpower and material resources are saved.
According to some embodiments of the invention, the age model training step comprises: acquiring an age label corresponding to the face feature vector; and taking the face feature vector and the age label as training data, and training through a fully-connected two-layer neural network and a loss function based on cross entropy to obtain the age identification model.
According to some embodiments of the invention, the age identifying step comprises: acquiring a face picture to be recognized, and acquiring a corresponding face feature vector to be recognized according to a backbone network of the face depth recognition model; taking the facial feature vector to be recognized as input data, and obtaining the probability corresponding to the age classification according to the age recognition model; and obtaining the identification age according to the age classification and the probability.
According to some embodiments of the invention, the age-identifying acquisition method comprises:
N＝∑(ni*pi)，
wherein N represents the identified age, NiIndicates the age, p, corresponding to the ith said age classificationiRepresenting the probability of the ith said age classification.
According to some embodiments of the invention, the ages are classified into 100, corresponding to an integer of ages 1 to 100, respectively.
According to some embodiments of the present invention, the fixed number of channels of the face feature vector is 512 dimensions.
According to some embodiments of the invention, the face age data set comprises: MORPH II face age dataset and FG-NET face age dataset.
According to some embodiments of the invention, the backbone network of the face depth recognition model comprises: a 100-layer deep convolutional neural network ResNet.
According to the face age recognition device of the embodiment of the second aspect of the invention, the method of the embodiment of the first aspect of the invention comprises the following steps: the feature vector acquisition module is used for acquiring face feature vectors with fixed channel numbers according to a main network of a face depth recognition model based on a face age data set; the age model training module is used for training and generating a plurality of age classification age identification models through two layers of neural networks according to the human face feature vector; and the age identification module is used for acquiring a face picture to be identified, acquiring a face feature vector to be identified according to the backbone network of the face depth identification model, and acquiring an identification age according to the age identification model.
The face age recognition apparatus according to the embodiment of the present invention has at least the same advantageous effects as those of the embodiment of the first aspect of the present invention.
A computer-readable storage medium according to an embodiment of the third aspect of the invention has stored thereon a computer program which, when executed by a processor, performs the method of the embodiment of the first aspect of the invention.
The computer-readable storage medium according to an embodiment of the present invention has at least the same advantageous effects as the embodiment of the first aspect of the present invention.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The above and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a schematic flow chart illustrating steps of a method according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating an age identification step of a method according to an embodiment of the present invention;
FIG. 3 is a block diagram of the internal modules of the apparatus according to an embodiment of the present invention.
Reference numerals:
the system comprises a feature vector acquisition module 100, an age model training module 200 and an age identification module 300.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention.
In the description of the present invention, the meaning of a plurality of means is one or more, the meaning of a plurality of means is two or more, and more than, less than, more than, etc. are understood as excluding the present number, and more than, less than, etc. are understood as including the present number. If the first and second are described for the purpose of distinguishing technical features, they are not to be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated or implicitly indicating the precedence of the technical features indicated.
The noun explains:
deep convolutional neural network ResNet of 100 layers: a deep convolutional neural network structure.
MS-Celeb-1M: microsoft published face data sets.
MORPH II: a public face age data set.
FG-NET: a public face age data set.
MTCNN model: a face detection method.
Arcface: a loss function method for face recognition.
Referring to fig. 1, a method of an embodiment of the present invention includes: a face feature acquisition step, namely acquiring face feature vectors with fixed channel numbers according to a backbone network of an existing face depth recognition model based on a face age data set; an age model training step, namely receiving the face feature vector, and learning and training through two layers of neural networks to obtain age identification models of a plurality of age classifications; and an age identification step, namely acquiring a face picture to be identified, acquiring a face feature vector to be identified according to a backbone network of the face depth identification model, and acquiring an identification age according to the age identification model. According to the embodiment of the invention, the existing face depth recognition model is reused, the age can be recognized through the shallow neural network, and compared with the age depth recognition model retrained, manpower and material resources are saved, and the accuracy is improved compared with the method for recognizing the age directly through the shallow neural network.
In an embodiment of the present invention, the age model training step includes: acquiring an age label corresponding to the face feature vector; and taking the face feature vector and the corresponding age label as training data, and performing learning training through a fully-connected two-layer neural network and a loss function based on cross entropy to obtain an age identification model.
Taking a face depth recognition model with 100 layers of deep convolutional neural network ResNet as a main network and 512-dimensional output channels as an example, the training process of the age recognition model according to the existing face depth recognition model is as follows. Based on the face age data sets MORPH II and FG-NET, after the photos in the data sets are input into a backbone network of the face depth recognition model, a plurality of corresponding 512-dimensional face feature vectors can be generated; each facial feature vector may obtain a corresponding age label from the data set. The generated face feature vector is randomly divided into two parts according to a specific proportion, for example, 70% of the face feature vector is selected as a training set, a 100 multi-classification age model is trained through a two-layer network of a full-connection structure by adopting a function based on cross entropy through a loss function (the loss function is 100 age classifications are output and respectively correspond to 1 year to 100 years), after the training is finished, the rest 30% of photos are used as test data of the age model, the probability obtained by each age classification is multiplied by the corresponding age and summed to obtain the specific age corresponding to each photo, then the difference between the actual age and the actual age is calculated, and finally the average error of the age model is verified to be 3.9 years. According to the embodiment of the invention, the face depth recognition model is multiplexed to obtain the shallow age recognition model generated by the obtained face feature vector, so that a recognition result with higher precision can be obtained.
In the embodiment of the present invention, the first and second substrates,the age identification model is a multi-classification age identification model, each classification corresponds to an age classification and has a corresponding age value. Referring to fig. 2, the method of obtaining the identification age is: acquiring a face picture to be recognized, and acquiring a corresponding face feature vector to be recognized according to a backbone network of a face depth recognition model; the face feature vector to be recognized is used as input data, and the probability corresponding to each age classification of the age recognition model can be obtained; then, according to the age classification and the probability, the identification age is obtained, and the calculation method comprises the following steps: n ═ Σ (N)i*pi) Wherein N represents the recognition age, NiIndicates the age, p, corresponding to the ith age categoryiRepresenting the probability of the ith age category.
Referring to fig. 3, the apparatus of an embodiment of the present invention includes: a feature vector acquisition module 100, an age model training module 200, and an age identification module 300. The feature vector acquisition module 100 is configured to acquire a face feature vector with a fixed number of channels according to a backbone network of a face depth recognition model based on a face age data set; the age model training module 200 is used for learning and training to generate a plurality of age-classified age identification models through two layers of neural networks according to the face feature vector; the age recognition module 300 is configured to obtain a face picture to be recognized, obtain a face feature vector to be recognized according to a backbone network of the face depth recognition model, and obtain a recognition age according to the age recognition model. In the embodiment of the invention, the feature vector acquisition module 100 acquires the face feature vector by using the existing face depth recognition model, and the face feature vector is sent to the age model training module 200 as training data to generate a two-layer age recognition model. The face picture to be recognized is processed by the feature vector acquisition module 100, and the recognized age is obtained by the age recognition module 300 through a trained age recognition model.
Although specific embodiments have been described herein, those of ordinary skill in the art will recognize that many other modifications or alternative embodiments are equally within the scope of this disclosure. For example, any of the functions and/or processing capabilities described in connection with a particular device or component may be performed by any other device or component. In addition, while various illustrative implementations and architectures have been described in accordance with embodiments of the present disclosure, those of ordinary skill in the art will recognize that many other modifications of the illustrative implementations and architectures described herein are also within the scope of the present disclosure.
Certain aspects of the present disclosure are described above with reference to block diagrams and flowchart illustrations of systems, methods, apparatus and/or computer program products according to example embodiments. It will be understood that one or more blocks of the block diagrams and flowchart illustrations, and combinations of blocks in the block diagrams and flowchart illustrations, respectively, can be implemented by executing computer-executable program instructions. Also, according to some embodiments, some blocks of the block diagrams and flow diagrams may not necessarily be performed in the order shown, or may not necessarily be performed in their entirety. In addition, additional components and/or operations beyond those shown in the block diagrams and flow diagrams may be present in certain embodiments.
Accordingly, blocks of the block diagrams and flowchart illustrations support combinations of means for performing the specified functions, combinations of elements or steps for performing the specified functions and program instruction means for performing the specified functions. It will also be understood that each block of the block diagrams and flowchart illustrations, and combinations of blocks in the block diagrams and flowchart illustrations, can be implemented by special purpose hardware-based computer systems that perform the specified functions, elements or steps, or combinations of special purpose hardware and computer instructions.
Program modules, applications, etc. described herein may include one or more software components, including, for example, software objects, methods, data structures, etc. Each such software component may include computer-executable instructions that, in response to execution, cause at least a portion of the functionality described herein (e.g., one or more operations of the illustrative methods described herein) to be performed.
The software components may be encoded in any of a variety of programming languages. An illustrative programming language may be a low-level programming language, such as assembly language associated with a particular hardware architecture and/or operating system platform. Software components that include assembly language instructions may need to be converted by an assembler program into executable machine code prior to execution by a hardware architecture and/or platform. Another exemplary programming language may be a higher level programming language, which may be portable across a variety of architectures. Software components that include higher level programming languages may need to be converted to an intermediate representation by an interpreter or compiler before execution. Other examples of programming languages include, but are not limited to, a macro language, a shell or command language, a job control language, a scripting language, a database query or search language, or a report writing language. In one or more exemplary embodiments, a software component containing instructions of one of the above programming language examples may be executed directly by an operating system or other software component without first being converted to another form.
The software components may be stored as files or other data storage constructs. Software components of similar types or related functionality may be stored together, such as in a particular directory, folder, or library. Software components may be static (e.g., preset or fixed) or dynamic (e.g., created or modified at execution time).
The embodiments of the present invention have been described in detail with reference to the accompanying drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge of those skilled in the art without departing from the gist of the present invention.
Claims (10)
1. A face age identification method is characterized by comprising the following steps:
a face feature acquisition step, namely acquiring face feature vectors with fixed channel numbers according to a backbone network of a face depth recognition model based on a face age data set;
an age model training step, namely learning and training to generate a plurality of age-classified age identification models through two layers of neural networks according to the face feature vector;
and an age identification step, namely acquiring a face picture to be identified, acquiring a face feature vector to be identified according to the backbone network of the face depth identification model, and acquiring an identification age according to the age identification model.
2. The face age recognition method of claim 1, wherein the age model training step comprises:
acquiring an age label corresponding to the face feature vector;
and taking the face feature vector and the age label as training data, and performing learning training through a fully-connected two-layer neural network and a loss function based on cross entropy to obtain the age identification model.
3. The face age identification method according to claim 1, wherein the age identification step includes:
acquiring a face picture to be recognized, and acquiring a corresponding face feature vector to be recognized according to a backbone network of the face depth recognition model;
taking the facial feature vector to be recognized as input data, and obtaining the probability corresponding to the age classification according to the age recognition model;
and obtaining the identification age according to the age classification and the probability.
4. The method for identifying the face age according to claim 3, wherein the method for acquiring the identified age comprises:
N＝∑(ni*pi)，
wherein N represents the identified age, NiIndicates the age, p, corresponding to the ith said age classificationiRepresenting the probability of the ith said age classification.
5. The face age identification method of claim 1, wherein the ages are classified into 100, each corresponding to an integer of ages 1 to 100.
6. The face age identification method according to claim 1, wherein the fixed number of channels of the face feature vector is 512 dimensions.
7. The face age recognition method of claim 1, wherein the face age data set comprises: MORPH II face age dataset and FG-NET face age dataset.
8. The face age recognition method of claim 1, wherein the backbone network of the face depth recognition model comprises: a 100-layer deep convolutional neural network ResNet.
9. A face age recognition device using the method of any one of claims 1 to 8, comprising:
the feature vector acquisition module is used for acquiring face feature vectors with fixed channel numbers according to a main network of a face depth recognition model based on a face age data set;
the age model training module is used for learning and training to generate a plurality of age-classified age identification models through two layers of neural networks according to the face feature vector;
and the age identification module is used for acquiring a face picture to be identified, acquiring a face feature vector to be identified according to the backbone network of the face depth identification model, and acquiring an identification age according to the age identification model.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method of any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010676911.1A CN111931586A (en) | 2020-07-14 | 2020-07-14 | Face age identification method and device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010676911.1A CN111931586A (en) | 2020-07-14 | 2020-07-14 | Face age identification method and device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111931586A true CN111931586A (en) | 2020-11-13 |
Family
ID=73312998
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010676911.1A Pending CN111931586A (en) | 2020-07-14 | 2020-07-14 | Face age identification method and device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111931586A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106503623A (en) * | 2016-09-27 | 2017-03-15 | 中国科学院自动化研究所 | Facial image age estimation method based on convolutional neural networks |
| CN107977633A (en) * | 2017-12-06 | 2018-05-01 | 平安科技（深圳）有限公司 | Age recognition methods, device and the storage medium of facial image |
| CN109670437A (en) * | 2018-12-14 | 2019-04-23 | 腾讯科技（深圳）有限公司 | Age prediction model training method, face-image recognition methods and device |
-
2020
- 2020-07-14 CN CN202010676911.1A patent/CN111931586A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106503623A (en) * | 2016-09-27 | 2017-03-15 | 中国科学院自动化研究所 | Facial image age estimation method based on convolutional neural networks |
| CN107977633A (en) * | 2017-12-06 | 2018-05-01 | 平安科技（深圳）有限公司 | Age recognition methods, device and the storage medium of facial image |
| CN109670437A (en) * | 2018-12-14 | 2019-04-23 | 腾讯科技（深圳）有限公司 | Age prediction model training method, face-image recognition methods and device |
Non-Patent Citations (1)
| Title |
|---|
| 丁大钧: "年龄估计技术综述", pages 1 - 8, Retrieved from the Internet <URL:https://zhuanlan.zhihu.com/p/63396344> * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111985323B (en) | Face recognition method and system based on deep convolutional neural network | |
| CN109034069B (en) | Method and apparatus for generating information | |
| CN111243601B (en) | Voiceprint clustering method and device, electronic equipment and computer-readable storage medium | |
| US20180260735A1 (en) | Training a hidden markov model | |
| CN107291775B (en) | Method and device for generating repairing linguistic data of error sample | |
| US20200349425A1 (en) | Training time reduction in automatic data augmentation | |
| CN113158656B (en) | Ironic content recognition method, ironic content recognition device, electronic device, and storage medium | |
| CN113536999A (en) | Character emotion recognition method, system, medium and electronic device | |
| CN111538809A (en) | Voice service quality detection method, model training method and device | |
| CN109408175B (en) | Real-time interaction method and system in general high-performance deep learning calculation engine | |
| CN111368066B (en) | Method, apparatus and computer readable storage medium for obtaining dialogue abstract | |
| CN113128284A (en) | Multi-mode emotion recognition method and device | |
| CN111222854A (en) | Interview method, device and equipment based on interview robot and storage medium | |
| CN111488950B (en) | Classification model information output method and device | |
| CN110852082B (en) | Synonym determination method and device | |
| CN113869398A (en) | Unbalanced text classification method, device, equipment and storage medium | |
| WO2020059545A1 (en) | Image classifier learning device, image classifier learning method, and program | |
| CN111931586A (en) | Face age identification method and device and storage medium | |
| CN112926515B (en) | Living body model training method and device | |
| CN114780757A (en) | Short media label extraction method and device, computer equipment and storage medium | |
| KR102476334B1 (en) | Diary generator using deep learning | |
| CN114676705A (en) | Dialogue relation processing method, computer and readable storage medium | |
| CN108021918B (en) | Character recognition method and device | |
| CN113657445B (en) | Resnet-based single-row text picture comparison method and system | |
| CN115049899B (en) | Model training method, reference expression generation method and related equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |